Estimating and Implementing Conventional Fairness Metrics With Probabilistic Protected Features
Keywords: fairness, anti-discrimination, measuring, disparity, disparity reduction, enforcing fairness, probabilistic protected attribute
TL;DR: We introduce a new method of (1) measuring ground truth fairness violations, and (2) training fair models, in a setting with very limited access to protected attribute data--a common setting in a wide range of government and business contexts.
Abstract: The vast majority of techniques to train fair models require access to the protected attribute (e.g., race, gender), either at train time or in production. However, in many practically important applications this protected attribute is largely unavailable. In this paper, we develop methods for measuring and reducing fairness violations in a setting with limited access to protected attribute labels. Specifically, we assume access to protected attribute labels on a small subset of the dataset of interest, but only probabilistic estimates of protected attribute labels (e.g., via Bayesian Improved Surname Geocoding or BISG) for the rest of the dataset. With this setting in mind, we propose a method for measuring common fairness metrics for an existing classifier, as well as a method for training a model to limit fairness violations by solving a constrained non-convex optimization problem. Unlike similar existing approaches, our methods take advantage of contextual information -- specifically, the relationships between a model's predictions and the probabilistic prediction of protected attributes, given the true protected attribute, and vice versa -- to provide tighter bounds on the true disparity. We provide an empirical illustration of our methods using voting data. First, we show our measurement method can bound the true disparity up to 5.5x tighter than previous methods in these applications. Then, we demonstrate that our training technique effectively reduces disparity in comparison to an unconstrained model while incurring lesser fairness-accuracy trade-offs than other fair optimization methods with limited access to protected attributes.
Supplementary Material: pdf
Primary Area: societal considerations including fairness, safety, privacy
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 3683
Loading